Upload config.json with huggingface_hub

config.json

@@ -1,37 +1,47 @@
 {
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
   "architectures": [
-    "XLMRobertaForSequenceClassification"
+    "MBartForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
+  "attention_dropout": 0.0,
   "bos_token_id": 0,
-  "classifier_dropout": null,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
   "eos_token_id": 2,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
   "id2label": {
     "0": 0,
     "1": 1,
     "2": 2
   },
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
   "label2id": {
     "0": 0,
     "1": 1,
     "2": 2
   },
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
-  "num_attention_heads": 12,
+  "max_position_embeddings": 1024,
+  "model_type": "mbart",
   "num_hidden_layers": 12,
   "pad_token_id": 1,
-  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
+  "scale_embedding": false,
+  "tokenizer_class": "BartphoTokenizer",
   "torch_dtype": "float32",
   "transformers_version": "4.52.4",
-  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 15004
+  "vocab_size": 40030
 }